MDP

Benchmarks

Task Name	Dataset Name	SOTA Result
Entropy Estimation	MDP M1	Estimated Entropy1.023	6
Entropy Estimation	MDP M2	Estimated Entropy1.324	3
Gittins index estimation	MDP	Maximum Estimation Error0.135	3
Minimal Entropy Strategy Synthesis	MDP M4	EntAns0.693	1
Minimal Entropy Strategy Synthesis	MDP M3	Entropy Answer1.099	1
Entropy Estimation	MDP M5	Exp(Estimated Entropy)2.954	1
Entropy Estimation	MDP M4	Exp(Estimated Entropy)2	1
Entropy Estimation	MDP M3	Exp(Estimated Entropy)3	1
Near-optimal policy identification	MDP	Metric-	0
Transfer Reinforcement Learning	MDP with Tucker rank (d, d, d)	Metric-	0
Transfer Reinforcement Learning	MDP with Tucker rank (S, S, d)	Metric-	0
Compute epsilon-optimal policy	MDP sample setting	Metric-	0

Showing 12 of 12 rows